Instructions to use pszemraj/tiny-gpt2-magicprompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/tiny-gpt2-magicprompt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="pszemraj/tiny-gpt2-magicprompt")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/tiny-gpt2-magicprompt")
model = AutoModelForCausalLM.from_pretrained("pszemraj/tiny-gpt2-magicprompt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/tiny-gpt2-magicprompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/tiny-gpt2-magicprompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/tiny-gpt2-magicprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pszemraj/tiny-gpt2-magicprompt

SGLang

How to use pszemraj/tiny-gpt2-magicprompt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "pszemraj/tiny-gpt2-magicprompt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/tiny-gpt2-magicprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "pszemraj/tiny-gpt2-magicprompt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/tiny-gpt2-magicprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/tiny-gpt2-magicprompt with Docker Model Runner:
```
docker model run hf.co/pszemraj/tiny-gpt2-magicprompt
```

tiny-gpt2-magicprompt / README.md

pszemraj

SFconvertbot

Super-squash branch 'main' using huggingface_hub

1722b64 verified 9 months ago

preview code

Raw History Blame Contribute Delete

2.24 kB

metadata

tags:
  - generated_from_trainer
  - stable diffusion
  - beautiful
  - masterpiece
datasets:
  - Gustavosta/Stable-Diffusion-Prompts
model-index:
  - name: tiny-gpt2-magicprompt
    results: []
widget:
  - text: morning sun over Jakarta
    example_title: morning sun
  - text: 'WARNING: pip is'
    example_title: pip
  - text: sentient cheese
    example_title: sentient cheese
  - text: cheeps are
    example_title: cheeps
parameters:
  min_length: 32
  max_length: 64
  no_repeat_ngram_size: 1
  do_sample: true

tiny-gpt2-magicprompt

~~Generate/augment your prompt, stable diffusion style.~~ Enter a new dimension of creativity

This model is a fine-tuned version of sshleifer/tiny-gpt2 on the Gustavosta/Stable-Diffusion-Prompts dataset. It achieves the following results on the evaluation set:

Loss: 10.7918
perplexity: 48618.8756

Intended uses & limitations

???

Training and evaluation data

refer to the Gustavosta/Stable-Diffusion-Prompts dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 32
total_train_batch_size: 512
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
10.8201	0.96	16	10.8191
10.8167	1.96	32	10.8145
10.8117	2.96	48	10.8095
10.8058	3.96	64	10.8025
10.7997	4.96	80	10.7989
10.7959	5.96	96	10.7947
10.7934	6.96	112	10.7925
10.7924	7.96	128	10.7919
10.7921	8.96	144	10.7918
10.792	9.96	160	10.7918

Framework versions

Transformers 4.25.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.6.1
Tokenizers 0.13.1